Complex weather traffic safety warning method and system based on vehicle-road collaboration

Abstract

The present invention relates to the field of intelligent transportation technology, and more specifically, to a complex weather traffic safety warning method and system based on vehicle-road collaboration, comprising the following steps: obtaining regional traffic information data; obtaining regional road condition information data; obtaining a road condition integration index; based on a driving safety index calculation module, performing multi-layer progressive calculations on the road condition integration index to obtain a driving safety index; based on a driving state prediction module, performing driving state analysis on the driving safety index through a recursive prediction algorithm to obtain a driving state prediction result; generating accurate warning information through a warning information generation module and pushing it to relevant vehicles to achieve accurate traffic safety warnings, and through collaborative data dynamic prediction compensation, road condition information adaptive integration, recursive driving safety index calculation and linkage feedback warning generation technology, the accuracy and transmission efficiency of the warning information are fundamentally improved, and the real-time response capability of the system is significantly enhanced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and more specifically, to a complex weather traffic safety warning method and system based on vehicle-road collaboration. Background Art

[0002] At present, with the development of intelligent transportation systems and the popularization of vehicle networking technology, the issue of traffic safety under complex weather conditions has attracted widespread attention. In severe weather, such as heavy rain, dense fog, snow, etc., road conditions become extremely complicated and can easily cause traffic accidents. Especially in high-traffic scenes such as highways and urban main roads, severe weather conditions have a significant impact on the driver's vision, road grip, etc., further increasing the probability of accidents. Therefore, technologies that can monitor and analyze road condition data in real time and generate accurate traffic safety warning information have become a key demand in the field of intelligent transportation.

[0003] Existing traffic safety warning systems are mostly based on static algorithms and simple data collection models, usually relying only on fixed traffic information collection modules and basic road condition information collection modules, and calculating the driving safety index through static weight settings. However, this static method often seems powerless when dealing with changing weather conditions. Traditional systems mainly rely on a single sensor, such as using only basic data such as vehicle speed and traffic flow, and lack a dynamic data compensation mechanism. When data collection is delayed or missing, the system cannot compensate in real time, resulting in a significant decrease in the accuracy of the driving safety index, a lag in warning information, and even false alarms or missed alarms, increasing traffic hazards.

[0004] In addition, existing methods usually use a fixed-weight driving safety index calculation method, which lacks flexibility for severe weather conditions and cannot adaptively adjust the calculation model according to actual road conditions. For example, in the risk assessment of snowy roads and rainy days, the weight settings used by existing technologies often cannot effectively reflect the actual slipperiness of the road, resulting in underestimation or overestimation of the driving safety index. This static calculation method not only performs poorly in severe weather conditions, but is also prone to distortion of the warning effect due to sudden weather changes, and cannot provide drivers with accurate safety tips in a timely manner.

[0005] More importantly, the generation and push of existing warning information usually adopts a single channel of traditional broadcast or vehicle-mounted system, resulting in a long delay in information transmission. Especially in traffic-intensive areas, traditional methods lack a real-time linkage mechanism, and the information diffusion efficiency is low. It is difficult to transmit warning information to subsequent vehicles in a short time, increasing the risk of secondary accidents.

[0006] In summary, the existing technology has significant deficiencies in dynamic data compensation, adaptive weight adjustment, linkage warning push, etc., especially in complex weather and high-density traffic conditions, which needs to be improved. In response to the above problems, the present invention proposes a complex weather traffic safety warning method based on vehicle-road collaboration, which is based on more advanced data collection and analysis technology, dynamic algorithm model and efficient information push mechanism to achieve effective warning of driving safety in complex weather. Summary of the invention

[0007] In response to the limitations of the above-mentioned prior art, the present invention proposes a complex weather traffic safety warning method and system based on vehicle-road collaboration, which aims to solve the problem that the prior art cannot effectively handle dynamic data missing and lag, and realize real-time and accurate safety warning through adaptive weighting and progressive driving safety index calculation.

[0008] The present invention provides a complex weather traffic safety warning method based on vehicle-road collaboration, comprising the following steps: based on a traffic information collection module, collecting vehicle speed, vehicle flow, vehicle type and traffic accident information in the area to be warned, and obtaining traffic information data of the area; based on a road condition information collection module, collecting road surface humidity, temperature and snow accumulation in the area, and obtaining road condition information data of the area; integrating the traffic information data and the road condition information data through a data fusion module to obtain a road condition integration index; based on a driving safety index calculation module, performing multi-layer progressive calculation on the road condition integration index to obtain a driving safety index; based on a driving state prediction module, performing driving state analysis on the driving safety index through a recursive prediction algorithm to obtain a driving state prediction result; generating accurate warning information through a warning information generation module and pushing it to relevant vehicles to achieve accurate traffic safety warning.

[0009] Preferably, the traffic information collection module includes a collaborative traffic data dynamic prediction and compensation algorithm, which is used to dynamically compensate and predict the vehicle speed, vehicle flow and traffic accident information through a collaborative compensation function to reduce data collection delay and loss and obtain complete traffic information data. The collaborative compensation function is defined as follows:

[0010] ,

[0011] in, is the vehicle speed collected in real time, is the current time, For traffic flow, is the attenuation coefficient, which indicates the attenuation of data due to acquisition delay. For the front Traffic flow in a time period, Dynamic weight for each cycle.

[0012] Preferably, the road condition information collection module includes a road condition information adaptive weight integration algorithm for dynamically weighted integration of the humidity, temperature and snow conditions based on an adaptive Gaussian weighting function to obtain a dynamic road condition integration index R.

[0013] Preferably, the driving safety index calculation module includes a multi-layer progressive driving safety index calculation algorithm for calculating the driving safety index based on the road condition integration index through a multi-layer progressive model. The expression is as follows:

[0014] ,

[0015] in, is the normalized vehicle speed, defined as the ratio of the current vehicle speed to the maximum vehicle speed of the road section, is the road condition integration index, To calculate the number of layers, the final driving safety index is calculated progressively through the output of each layer.

[0016] Preferably, the driving state prediction module includes a driving state recursive prediction optimization algorithm for obtaining a driving state prediction result through a collaborative recursive model based on the driving safety index. The expression is as follows:

[0017] ,

[0018] in, is the driving safety index, is the synergistic attenuation coefficient, is the road condition integration index, is the number of recursion layers.

[0019] Preferably, the warning information generation module includes an accurate warning generation and iterative feedback push algorithm, which is used to generate warning information based on the driving state prediction result and push it to the relevant vehicles. The expression is as follows:

[0020] ,

[0021] in, is the driving status prediction result, To push the enhancement factor, is the distance between vehicles, is the distance attenuation coefficient. When the distance between the vehicle receiving the warning and the vehicle in front is less than 150 meters, the nearest vehicle will pass the command to the subsequent vehicles to realize the linkage diffusion of the warning information.

[0022] Preferably, the traffic information data and road condition information data are integrated through the data fusion module to obtain a dynamic road condition integration index to provide input to the driving safety index calculation module, so that the driving safety index calculation module can perform progressive analysis based on multiple factors to adapt to complex weather conditions.

[0023] Preferably, the output of the driving safety index calculation module is associated with the input of the driving state prediction module to ensure that the driving state prediction is real-time and optimize the accuracy of driving state judgment through a recursive prediction model.

[0024] Preferably, the warning information generation module generates the warning information through the prediction result obtained by the driving state prediction module, and pushes the warning information to the corresponding vehicle through the V2X communication technology to achieve real-time and dynamic driving safety warning; the precise warning generation and iterative feedback push algorithm forms a feedback loop between neighboring vehicles through the synergistic effect of the distance attenuation and the push enhancement factor, thereby improving the transmission speed and accuracy of the warning information and achieving global driving safety warning.

[0025] The complex weather traffic safety warning system based on vehicle-road collaboration for executing the method includes:

[0026] A traffic information collection module is used to collect vehicle speed, vehicle flow, vehicle type and traffic accident information in the area to be warned, so as to obtain traffic information data in the area; a road condition information collection module is used to collect road surface humidity, temperature and snow accumulation in the area, so as to obtain road condition information data in the area; a data fusion module is used to integrate the traffic information data and the road condition information data to generate a road condition integration index; a driving safety index calculation module is used to obtain a driving safety index through multi-layer progressive calculation based on the road condition integration index; a driving state prediction module is used to generate a driving state prediction result based on the driving safety index; a warning information generation module is used to generate warning information based on the driving state prediction result and push it to relevant vehicles to achieve accurate traffic safety warning.

[0027] The present invention has the following beneficial effects:

[0028] The present invention fundamentally improves the accuracy and transmission efficiency of early warning information and significantly enhances the real-time response capability of the system through the coordinated data dynamic prediction compensation, road condition information adaptive integration, recursive driving safety index calculation and linkage feedback early warning generation technology. To achieve the above goals, the present invention adopts a multi-layer progressive algorithm and an adaptive weighted processing mechanism, so that the system can be flexibly adjusted under different weather conditions and respond quickly to emergencies, thereby effectively reducing the occurrence of traffic accidents.

[0029] The present invention overcomes many bottlenecks in the prior art through a series of innovative algorithm designs and module optimizations. First, based on the design of a collaborative traffic data dynamic prediction and compensation algorithm, the system can effectively deal with delays and missing issues during data collection. By dynamically predicting and compensating for real-time data such as vehicle speed and traffic volume, the present invention effectively improves the continuity and reliability of the data, so that the calculation of the driving safety index remains highly accurate even when data is missing.

[0030] Secondly, the present invention realizes adaptive adjustment of humidity, temperature and snow information under different weather conditions through an adaptive weight integration algorithm for road condition information combined with Gaussian weighting processing. Compared with the traditional fixed weight algorithm, the present invention can flexibly adjust the weighting parameters under complex weather conditions, so that the calculation of the driving safety index is more in line with the actual road conditions. This adaptive adjustment can not only significantly enhance the system's ability to respond to sudden weather changes, but also more accurately assess traffic risks under high-risk weather conditions such as snow and rain, making the warning information more instructive.

[0031] Furthermore, the multi-layer recursive driving safety index calculation algorithm of the present invention adopts a progressive layered calculation mode in the calculation process of the driving safety index, and realizes dynamic and accurate calculation of the driving safety index through multi-level recursive optimization. This progressive calculation method enables the system to maintain a high degree of response even in high-density traffic and sudden changes in road conditions, reducing the error accumulation problem caused by static methods. This dynamic adjustment and progressive calculation make the calculation results of the driving safety index more accurate and real-time, and can provide real-time feedback on changes in complex weather and road conditions.

[0032] Finally, in the process of generating and pushing warning information, the present invention uses precise warning generation and iterative feedback push algorithm design, combined with distance attenuation and push enhancement factors, to enable the warning information to be quickly transmitted between adjacent vehicles, forming an efficient and linked feedback mechanism. This mechanism optimizes the traditional static broadcast method and achieves more accurate point-to-point information transmission through V2X communication, especially in high-density traffic conditions, which can quickly transmit to adjacent vehicles, avoiding delays and information loss in information transmission, thereby effectively reducing the risk of secondary accidents.

[0033] In summary, the present invention has achieved multi-dimensional improvements in collaborative data compensation, adaptive weight adjustment, multi-layer progressive calculation, and linkage feedback push, greatly enhancing the system's traffic safety warning performance under complex weather conditions. The present invention is not only superior to the existing technology in terms of accuracy and real-time information processing, but also significantly improves the effect of traffic safety warning through collaborative complementarity and dynamic adjustment among various algorithm modules. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1The figure is a logic block diagram of the method of the present invention.

[0035] Figure 2 This is a logic block diagram of early warning information generation and push in the present invention.

[0036] Figure 3 This is a logical block diagram of the traffic and road condition information collection and fusion of the present invention.

[0037] Figure 4 This is a logic block diagram for iterative feedback push of early warning information of the present invention. DETAILED DESCRIPTION

[0038] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects thereof are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0039] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0040] Please refer to Figure 1-4 The present invention discloses a complex weather traffic safety warning method and system based on vehicle-road collaboration, aiming to achieve efficient and accurate traffic safety warning under complex weather conditions. Through multi-level and progressive data collection and calculation algorithms, the present invention has made innovative designs in the collection, integration, prediction and push of real-time traffic information, improving data accuracy and warning response speed.

[0041] The core method of the present invention first includes a traffic information collection module 1 and a road condition information collection module 2. The traffic information collection module 1 is used to collect vehicle speed, traffic volume, vehicle type and traffic accident information in the area to be warned, so as to obtain comprehensive traffic data input. Here, the vehicle speed information is collected through GPS, vehicle-mounted sensors and radar to ensure the complementarity of different devices in data delay and data accuracy. For example, when the weather conditions are good, radar and vehicle-mounted sensors can provide accurate vehicle speed information, but in low visibility conditions such as foggy days, GPS can be used as a redundant data source. Preferably, when the data delay is controlled within 1 second, the single sensor error can be effectively reduced in combination with the data compensation method.

[0042] Next, the road condition information collection module 2 collects the humidity, temperature and snow conditions of the road to obtain the actual road condition data. Under snow conditions, the system can identify the thickness of the snow in real time. For example, when the snow thickness is less than 2mm, the system defines it as low risk, when the thickness is between 2 and 4mm, it is defined as medium risk, and when it exceeds 4mm, it is defined as a high risk level. Such thickness differentiation enables the system to quickly judge the safety of road conditions and ensure dynamic adaptability to the impact of weather changes on traffic safety.

[0043] According to a preferred embodiment of the present invention, the traffic information collection module 1 further uses a collaborative traffic data dynamic prediction compensation algorithm to perform data compensation. The algorithm uses a collaborative compensation function to compensate for vehicle speed, vehicle flow and accident information, reducing delays and losses in data collection and improving data real-time and integrity. Specifically, the compensation function is defined as follows:

[0044] ,

[0045] in, Indicates the vehicle speed collected in real time. is a time variable, representing the current data collection time point, Represents traffic flow data, is the attenuation coefficient (the recommended value is 0.1, which is suitable for real-time data with a delay of about 1 second to smooth the delay effect in the data; Before Traffic flow in a time period, is the weighting coefficient for each cycle.

[0046] Preferably, in order to reduce the impact of environmental noise on rainy days, A relatively large weight (e.g., 0.8-0.9) can be used to ensure that the data compensation effect is more significant. At the same time, in the case of frequent accidents or missing data, the above compensation algorithm can generate near-real-time traffic information, providing reliable data input for subsequent steps.

[0047] According to a preferred embodiment of the present invention, the data fusion module 3 uses a road condition information adaptive weight integration algorithm to dynamically weight and integrate the humidity, temperature and snow thickness information to obtain a road condition integration index: .

[0048] Then, the driving safety index calculation module 4 calculates the driving safety index by a multi-layered driving safety index calculation algorithm. , providing a comprehensive indicator of driving safety. The algorithm is based on a progressive hierarchical model, integrating the road condition index Normalized speed Combined, ensure that the final driving safety index reflects the relationship between road conditions and real-time vehicle speed. The specific meter formula is:

[0049] ,

[0050] in, The normalized vehicle speed is the ratio of the current vehicle speed to the maximum allowed speed of the road section. Preferably, if the vehicle speed is much lower than the speed limit (such as lower than 50% of the speed limit), it is directly considered that the speed safety is high, thereby relatively improving the driving safety index; when the vehicle speed is close to or higher than the speed limit, the progressive layer A higher value (such as 5) can be taken to ensure that the driving safety index calculated progressively is more accurate. This multi-layer progressive mode enables the system to provide adaptive safety evaluation in both low-speed and high-speed scenarios.

[0051] According to a preferred embodiment of the present invention, the driving state prediction module 5 predicts the driving safety index through a driving state recursive prediction optimization algorithm to obtain a driving state prediction result. The algorithm dynamically optimizes the driving state through a collaborative recursive model, so that the system can adjust the prediction result in time according to the real-time driving safety index. The driving state prediction expression is as follows:

[0052] ,

[0053] in, is the driving safety index, is the road condition integration index, The synergistic attenuation coefficient is usually set to 0.8 in clear weather, and 0.6 in complex weather, such as heavy rain and fog, to make the recursive prediction more sensitive to changes in environmental conditions. Adjust according to the density of the road section, set it to 3 when the density is low, and preferably set it to 5 when the density is high. The above settings ensure that the prediction results of the driving status are highly accurate, thereby effectively dealing with traffic risks caused by complex weather.

[0054] In summary, the present invention realizes driving safety warning under complex weather conditions through multi-module collaboration, covering a progressive method of traffic information collection, road condition integration, driving safety index calculation and state prediction.

[0055] According to a preferred embodiment of the present invention, the warning information generation module 6 uses an accurate warning generation and iterative feedback push algorithm to ensure efficient push and delivery of warning information. The algorithm calculates the driving state prediction result based on the driving state prediction result. And combined with the feedback mechanism, accurate early warning information is generated. The formula for generating early warning information is as follows:

[0056] ,

[0057] in, To generate warning information, is the driving status prediction result, It is a push enhancement factor, which is used to control the intensity of early warning information transmission; Indicates the distance between the receiving vehicle and the vehicle in front, is the distance attenuation coefficient, which is used to appropriately weaken the warning effect when the distance increases to ensure the priority and effectiveness of information push. The empirical value is set to 1.0 at 150 meters, and gradually decreases to 0.5 after exceeding 150 meters to avoid the spread of warning information among unrelated vehicles.

[0058] Through this iterative feedback push algorithm, the vehicle that receives the warning will continue to pass the warning information to the subsequent vehicles, forming a chain linkage warning mechanism. For example, on a highway section, when a vehicle detects that the driving safety index is lower than the threshold (such as the safety index ), the system will automatically trigger the algorithm and quickly push warning information to the following vehicles, so that the following vehicles can slow down in time to avoid chain accidents. It is worth noting that the warning information generation module 5 automatically adjusts the feedback frequency under different traffic densities to give priority to pushing to close-range vehicles in high-density traffic, ensuring the accuracy and effectiveness of warning information dissemination.

[0059] According to a preferred embodiment of the present invention, traffic information data and road condition information data are integrated in the data fusion module 3 to obtain a more dynamic road condition integration index. , and provided to the driving safety index calculation module 3 as input, so as to realize multi-factor progressive analysis. Through this process, the driving safety index not only accurately reflects the real-time traffic and road conditions information, but also has real-time dynamic response capabilities. Preferably, in highway scenes with complex driving conditions, the data fusion module 3 will automatically adjust the weighting parameters according to the real-time collected humidity, temperature and snow conditions, so that the contribution factor of each factor changes dynamically over time. For example, on slippery roads, the weight of humidity is preferably increased to 1.3, while on sections with more snow, the weight of snow is increased to 1.5 to ensure the sensitivity of the driving safety index to different weather conditions.

[0060] Combined with actual application scenarios, when the weather changes suddenly, the system can automatically adjust the weight of each factor and quickly respond to the impact of different factors on driving safety, effectively enhancing the robustness of the system. For example, on the elevated section of the highway, when the snow accumulates more, the system will automatically increase the weight of the snow thickness and reduce the safety index of the section, so that the driver can get more real-time and reliable driving warnings.

[0061] According to a preferred embodiment of the present invention, the output of the driving safety index calculation module 4 is associated with the input of the driving state prediction module 5 in real time, ensuring that the driving state prediction has high real-time and accuracy. The driving safety index is a comprehensive indicator obtained through a multi-layer progressive calculation method. Therefore, in the process of driving state prediction, the dynamic adjustment of the driving safety index directly affects the judgment of the driving state. Preferably, when the driving safety index is lower than 0.4, the high priority mode of the state prediction is triggered, so that the system automatically switches to the emergency mode and optimizes the accuracy of the driving state prediction.

[0062] For example, in the case of high traffic density and complex road conditions, the driving state prediction module 5 will combine the latest driving safety index to make a progressive prediction of the driving state layer by layer, so that the prediction accuracy and dynamic adjustment ability are further improved. Through this association method, not only the accuracy of the driving state prediction is ensured, but also the response speed of the warning information is improved. Preferably, when the traffic congestion level reaches a medium level (such as the traffic volume reaches more than 100 vehicles per minute), the driving safety index prediction module will dynamically adjust the prediction model to make the prediction result of the driving state more stable, thereby providing a more efficient warning information output.

[0063] According to a preferred embodiment of the present invention, the warning information generation module 6 generates accurate warning information through the prediction results of the driving state prediction module 5, and pushes the warning information to the corresponding vehicle through the V2X communication technology to achieve real-time dynamic driving safety warning. V2X communication technology enables warning information to be quickly transmitted between vehicles, thereby forming a multi-node collaborative warning mechanism to effectively respond to emergencies in high-density traffic environments. Preferably, under the condition that the distance between vehicles is less than 150 meters, the warning information will be pushed to adjacent vehicles first to enhance the speed of information propagation. For example, when the system detects that the safety index is lower than a certain threshold (such as 0.2), the V2X communication system will push the warning information with high priority, so that adjacent vehicles can obtain the warning information in a very short time and take safety measures in time.

[0064] In addition, through the multi-node transmission mechanism of V2X, the system can also automatically adjust the transmission frequency and range of warning information. In bad weather conditions, such as foggy weather, the distance between vehicles may be too close due to poor visibility. At this time, the system can automatically increase the frequency of information push, so that warning information can be quickly transmitted between vehicles, thus avoiding traffic accidents.

[0065] According to a preferred embodiment of the present invention, the precise warning generation and iterative feedback push algorithm realizes the efficient transmission of warning information between adjacent vehicles through the synergistic effect of distance attenuation and push enhancement factor, forming a warning system with linkage feedback. This feedback mechanism can ensure the real-time and accuracy of warning information, especially in high-volume and high-density traffic scenarios, and can effectively improve the system's warning capability and transmission efficiency.

[0066] In actual applications, when the distance between the vehicle and the vehicle in front is less than 150 meters, the push factor is enhanced. The value of increases the rate of information propagation. For example, preferably, the push enhancement factor The empirical value is 1.2 within 150 meters, and it is reduced to 0.8 beyond 150 meters to ensure that information is transmitted to vehicles closer to the vehicle first. In addition, in sections with severe congestion, the distance attenuation coefficient It can be set to 0.7 to 0.9 to balance the information delivery rate and delivery coverage.

[0067] Furthermore, the feedback push algorithm can also dynamically adjust the feedback frequency and information intensity according to the real-time traffic density. When the traffic volume is large, for example, when the number of vehicles per minute exceeds 100, the system will automatically increase the feedback push frequency to once per second, so as to ensure that the following vehicles can obtain timely warning information and take appropriate deceleration measures.

[0068] According to a preferred embodiment of the present invention, the present invention further discloses a complex weather traffic safety warning system based on vehicle-road collaboration, comprising:

[0069] Traffic information collection module 1, used to collect vehicle speed, vehicle flow, vehicle type and traffic accident information in the area to be warned, so as to obtain traffic information data in the area;

[0070] The road condition information collection module 2 is used to collect the road humidity, temperature and snow accumulation in the area to obtain the road condition information data in the area;

[0071] A data fusion module 3, used for integrating the traffic information data and the road condition information data to generate a road condition integration index;

[0072] A driving safety index calculation module 4, used to obtain a driving safety index through multi-layer progressive calculation based on the road condition integration index;

[0073] A driving state prediction module 5, used to generate a driving state prediction result based on the driving safety index;

[0074] The warning information generation module 6 is used to generate warning information based on the driving state prediction result and push it to related vehicles to achieve accurate traffic safety warning.

[0075] In summary, the present invention realizes driving safety warning under complex weather conditions through multi-level and progressive module collaboration, covering the entire process of traffic information collection, road condition information integration, driving safety index calculation, driving status prediction, and warning information generation and push. In specific applications, the present invention can effectively improve driving safety in high-flow, high-density traffic environments and reduce the risk of traffic accidents in bad weather.

[0076] In order to verify the driving safety warning performance of the present invention under complex weather conditions, the present invention conducted a comparative study of the embodiment and the comparative experiment. By using professional traffic data sets, tests were carried out under various weather conditions and traffic flows to verify the superiority of the present invention in driving safety index calculation, driving state prediction and warning information generation. The traffic data set used in the test comes from the data platform of the domestic authoritative transportation department. The data set contains real vehicle speed, traffic flow, road condition information and weather data, covering complex weather environments such as rainy days, snowy days and foggy days.

[0077] In the embodiment of the present invention, a complex weather traffic safety warning system based on vehicle-road collaboration is used, which mainly includes a traffic information collection module 1, a road condition information collection module 2, a data fusion module 3, a driving safety index calculation module 4, a driving state prediction module 5 and a warning information generation module 6. In actual tests, the delayed and missing data are compensated by the collaborative traffic data dynamic prediction compensation algorithm, and the humidity, temperature and snow accumulation under different weather conditions are weighted by the road condition information adaptive weight integration algorithm, and finally accurate warning is achieved through the driving safety index and driving state prediction. During the test, the real-time transmission of warning information is achieved through V2X communication technology.

[0078] In the comparative test, the traditional traffic warning system based on static algorithm was used. The system only contained basic traffic information collection and road condition information collection modules, and did not have dynamic compensation and adaptive weighted processing functions. The driving safety index was calculated based on static weights, and the driving status prediction did not have real-time adjustment functions. The warning information was broadcast through the traditional vehicle-mounted system, and the transmission efficiency was low.

[0079] During the test, the following three key indicators were mainly compared to verify the superiority of the present invention:

[0080] 1. Accuracy of driving safety index: By comparing the relationship between the system's driving safety index calculation results and the traffic accident rate, the system's safety warning accuracy under complex weather conditions is evaluated. A driving safety index below 0.3 indicates high risk, 0.3 to 0.6 indicates medium risk, and above 0.6 indicates low risk.

[0081] 2. Response speed of driving state prediction: The response time (in seconds) of the system when the driving state changes is used for evaluation. In sudden traffic conditions (such as sudden braking or road congestion), the shorter the response time, the faster the system reacts to the sudden situation.

[0082] 3. Warning information transmission coverage rate: By measuring the distance range of warning information transmitted to the rear vehicles when the traffic density is medium to high (the number of vehicles per minute is 80-120), the warning coverage effect of the system is evaluated. A warning information coverage rate of more than 90% is considered excellent.

[0083] The test results are shown in Table 1, which shows in detail the performance of the embodiment of the present invention and the comparative example system in terms of driving safety index, driving state prediction response speed and warning information transmission coverage under complex weather conditions.

[0084] Table 1 Comparison of test results of the embodiment and the comparative example

[0085] ,

[0086] It can be seen from the test results in Table 1 that the present invention has a significant advantage in the accuracy of the driving safety index, reaching an accuracy of 0.82, which is 39% higher than the 0.59 of the comparative system. This shows that the present invention uses a multi-layer progressive driving safety index calculation algorithm and an adaptive weighting strategy under complex weather conditions to make the safety index more in line with the actual road conditions, thereby effectively warning of potential traffic risks and avoiding traffic accidents caused by weather reasons.

[0087] In addition, in terms of the response speed of the driving state prediction, the response time of the embodiment of the present invention is 1.2 seconds, while the response time of the comparative system is 2.8 seconds. The driving state recursive prediction optimization algorithm in the present invention can quickly identify and adjust the prediction results under sudden traffic conditions, so that the system can issue early warnings in time to avoid further expansion of accidents. This improvement in response speed is of great significance for high-density traffic and rapidly changing traffic environments.

[0088] The test results of the warning information transmission coverage rate further verified the efficiency and reliability of the present invention. Under medium to high density traffic, the present invention achieves a warning information transmission coverage rate of 92% through V2X communication technology and iterative feedback push algorithm, which is significantly better than the 68% of the comparative system. In the present invention, based on the synergistic effect of the vehicle distance attenuation coefficient and the push enhancement factor, the warning information can be quickly transmitted to adjacent vehicles, ensuring the accurate and efficient transmission of the warning information, and reducing the delay problem of information transmission under complex weather conditions.

[0089] To sum up, the embodiments of the present invention perform significantly better than traditional static traffic warning systems in terms of the accuracy of driving safety index, driving status prediction response speed and warning information transmission coverage, which effectively verifies the superiority of the present invention in complex weather traffic safety warning, especially in dealing with emergencies and high-density traffic environments.

[0090] It should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A complex weather traffic safety warning method based on vehicle-road collaboration, characterized in that: The method comprises the following steps: collecting vehicle speed, vehicle flow, vehicle type and traffic accident information of the area to be warned based on the traffic information collection module to obtain traffic information data of the area; The road condition information collection module collects the road humidity, temperature and snow conditions of the area to obtain the road condition information data of the area; the data fusion module integrates the traffic information data and the road condition information data to obtain the road condition integration index; the driving safety index calculation module performs multi-layer progressive calculation on the road condition integration index to obtain the driving safety index; Based on the driving state prediction module, the driving state analysis of the driving safety index is performed through a recursive prediction algorithm to obtain a driving state prediction result; accurate warning information is generated through the warning information generation module and pushed to relevant vehicles to achieve accurate traffic safety warning; The traffic information collection module includes a collaborative traffic data dynamic prediction and compensation algorithm, which is used to dynamically compensate and predict the vehicle speed, vehicle flow and traffic accident information through a collaborative compensation function to reduce data collection delay and loss and obtain complete traffic information data. The collaborative compensation function is defined as follows: ， in, is the vehicle speed collected in real time, is the current time, For traffic flow, is the attenuation coefficient, which indicates the attenuation of data due to acquisition delay. For the front Traffic flow in a time period, Dynamic weight for each cycle.

2. The method according to claim 1, characterized in that The road condition information collection module includes a road condition information adaptive weight integration algorithm for dynamically weighting and integrating the humidity, temperature and snow conditions based on an adaptive Gaussian weighting function to obtain a dynamic road condition integration index. .

3. The method according to claim 2, characterized in that The driving safety index calculation module includes a multi-layer progressive driving safety index calculation algorithm for calculating the driving safety index based on the road condition integration index through a multi-layer progressive model. The expression is as follows: ， in, is the normalized vehicle speed, defined as the ratio of the current vehicle speed to the maximum vehicle speed of the road section, is the road condition integration index, To calculate the number of layers, the final driving safety index is calculated progressively through the output of each layer.

4. The method according to claim 3, characterized in that The driving state prediction module includes a driving state recursive prediction optimization algorithm for obtaining a driving state prediction result through a collaborative recursive model based on the driving safety index. The expression is as follows: ， in, is the driving safety index, is the synergistic attenuation coefficient, is the road condition integration index, is the number of recursion layers.

5. The method according to claim 4, characterized in that The warning information generation module includes an accurate warning generation and iterative feedback push algorithm, which is used to generate warning information based on the driving state prediction result and push it to the relevant vehicles. The expression is as follows: ， in, is the driving status prediction result, is the push enhancement factor, is the distance between vehicles, is the distance attenuation coefficient. When the distance between the vehicle receiving the warning and the vehicle in front is less than 150 meters, the nearest vehicle will pass the command to the subsequent vehicles to realize the linkage diffusion of the warning information.

6. The method according to claim 5, characterized in that The traffic information data and road condition information data are integrated through the data fusion module to obtain a dynamic road condition integration index to provide input to the driving safety index calculation module, so that the driving safety index calculation module can perform progressive analysis based on multiple factors to adapt to complex weather conditions.

7. The method according to claim 6, characterized in that The output of the driving safety index calculation module is associated with the input of the driving state prediction module to ensure that the driving state prediction is real-time and optimize the accuracy of driving state judgment through a recursive prediction model.

8. The method according to claim 7, characterized in that The warning information generation module generates the warning information through the prediction result obtained by the driving state prediction module, and pushes the warning information to the corresponding vehicle through V2X communication technology to achieve real-time and dynamic driving safety warning; The precise warning generation and iterative feedback push algorithm enables the warning information to form a feedback loop between neighboring vehicles through the synergistic effect of the distance attenuation and the push enhancement factor, thereby improving the transmission speed and accuracy of the warning information and achieving global driving safety warnings.

9. A complex weather traffic safety warning system based on vehicle-road collaboration that executes the method of claim 1, characterized in that: include: Traffic information collection module, used to collect vehicle speed, vehicle flow, vehicle type and traffic accident information in the area to be warned, so as to obtain traffic information data in the area; A road condition information collection module is used to collect road humidity, temperature and snow conditions in the area to obtain road condition information data in the area; A data fusion module, used to integrate the traffic information data and the road condition information data to generate a road condition integration index; a driving safety index calculation module, used to obtain a driving safety index through multi-layer progressive calculation based on the road condition integration index; a driving state prediction module, used to generate a driving state prediction result based on the driving safety index; The warning information generation module is used to generate warning information based on the driving state prediction result and push it to relevant vehicles to achieve accurate traffic safety warning.

Images